© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 10093
    Prev
    Next
    INDEX
    Explanations

    references to political parties and figures, particularly related to Democratic and Republican contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.21
    1.2%
    410
    +0.16
    1.0%
    443
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.21
    0.03
    410
    +0.16
    0.03
    418
    +0.13
    0.00
    Negative Logits
    -2.73
    <|outofrange|>
    -2.73
    <|outofrange|>
    -2.73
    ↵↵
    -2.73
    ↵
    -2.73
    ↵
    -2.73
    ↵
    -2.73
    ↵
    -2.73
    ↵
    -2.73
    -2.73
    POSITIVE LOGITS
    vote
    1.96
     Party
    1.84
     nominee
    1.76
    election
    1.76
    footer
    1.70
    ulus
    1.69
    member
    1.69
    ford
    1.68
    ucci
    1.67
     leaders
    1.65
    Activations Density 0.200%

    No Known Activations